The goal of the RODYMAN project is the derivation of a unified framework for dynamic manipulation where the mobile nature of the robotic system and the manipulation of non-prehensile non-rigid or deformable objects will explicitly be taken into account. Novel techniques for 3D object perception, dynamic manipulation control and reactive planning will be proposed. An innovative mobile platform with a torso, two lightweight arms with multi-fingered hands, and a sensorized head will be developed for effective execution of complex manipulation tasks, also in the presence of humans. Dynamic manipulation will be tested on an advanced demonstrator, i.e. pizza making process, which is currently unfeasible with the prototypes available in the labs. The research results to be achieved in RODYMAN will contribute to paving the way towards enhancing autonomy and operational capabilities of service robots, with the ambitious goal of bridging the gap between robotic and human task execution capability.
The development and assembly of the first worldwide platform able to execute complex task in the field of dynamic manipulation is a central point for achieving robots with a truly human-like task execution capability (service robotics). A manipulator mounted on a mobile platform has a much larger workspace than a fixed one thanks to the additional mobility given by the wheels. As a consequence, a mobile manipulation system presents both advantages of mobility provided by a mobile platform and dexterity provided by the manipulator. Moreover, if a torso with two arms/hands and a head are mounted onto a mobile platform, a set-up with a dexterity similar to the human can be achieved, allowing the execution of complex tasks similar to those usually executed by humans.
All the current experimental dual-arm/hand mobile platforms have never been employed in non-prehensile tasks with deformable objects. For this reason, an advanced mobile robotic platform equipped with two light-weight arms and multi-fingered hands will be developed during the project. It will be endowed with sensors in such a way as to interact with deformable objects and recognize the presence of other robots/humans in the shared working space, in order to safely avoid them. This platform will be able to perform dynamic manipulation tasks, which are currently unfeasible, thus becoming a reference platform in the field of mobile manipulation for the next years.
A number of scholars at Ph.D. and Post-Doc level with developed high skills in perceptions, control, robotic (mobile) manipulation will be involved during this project. They are supposed to intensively work on this new platform, acquiring in such a way all the necessary competence to develop the future generations of mobile manipulation robots that will be available on the market.